Robust Stuttering Detection via Multi-task and Adversarial Learning

Shakeel Sheikh (1) , Md Sahidullah (1) , Fabrice Hirsch (2) , Slim Ouni (1)

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
2 Praxiling - Praxiling

By automatic detection and identification of stuttering, speech pathologists can track the progression of disfluencies of persons who stutter (PWS). In this paper, we investigate the impact of multi-task (MTL) and adversarial learning (ADV) to learn robust stutter features. This is the first-ever preliminary study where MTL and ADV have been employed in stuttering identification (SI). We evaluate our system on the SEP-28k stuttering dataset consisting of ≈ 20 hours of data from 385 podcasts. Our methods show promising results and outperform the baseline in various disfluency classes. We achieve up to 10%, 6.78%, and 2% improvement in repetitions, blocks, and interjections respectively over the baseline.

Mots clés: multi-tasking; metadata invariant; speech disorder; adversarial learning; stuttering; disfluency

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]; Traitement du signal et de l'image [eess.SP]

Shakeel Sheikh, Md Sahidullah, Fabrice Hirsch, Slim Ouni. Robust Stuttering Detection via Multi-task and Adversarial Learning. EUSIPCO 2022 - 30th European Signal Processing Conference, Aug 2022, Belgrade, Serbia. ⟨hal-03629785⟩